Title :
Optimally adapted indexing trees for medical image databases
Author :
Qian, Xiaoning ; Tagare, Hemant D.
Author_Institution :
Dept. of Diagnostic Radiol., Yale Univ., New Haven, CT, USA
Abstract :
Medical image databases often have high dimensional features and standard indexing trees do not perform well with them. In this paper, we propose an algorithm for eliminating nodes in the indexing tree so that the resulting tree has improved performance. The algorithm (provably) provides the least cost tree among all possible trees that can be generated by eliminating nodes. Experimental data about performance improvement in simulations and real world are provided.
Keywords :
PACS; database indexing; trees (mathematics); visual databases; all possible trees; content based image retrieval; least cost tree; medical diagnostic imaging; medical image databases; nodes elimination algorithm; optimally adapted indexing trees; similarity measure; simulations performance improvement; user-defined threshold; Biomedical imaging; Computed tomography; Content based retrieval; Image databases; Image retrieval; Indexing; Information retrieval; Medical diagnostic imaging; Spatial databases; Testing;
Conference_Titel :
Biomedical Imaging, 2002. Proceedings. 2002 IEEE International Symposium on
Print_ISBN :
0-7803-7584-X
DOI :
10.1109/ISBI.2002.1029258
